Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    articles and descriptors used to characterize individuals or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fn
    -0.81
    answer
    -0.79
    Edit
    -0.79
    uden
    -0.78
    tone
    -0.76
    events
    -0.75
    attacks
    -0.72
    advertisement
    -0.71
    encies
    -0.71
    EMA
    -0.70
    POSITIVE LOGITS
     member
    1.14
     staunch
    1.11
     prolific
    1.09
     descendant
    1.07
     fixture
    1.04
     supporter
    1.03
     proud
    1.03
     lifelong
    1.01
     longtime
    1.00
     devout
    1.00
    Act Density 0.106%

    No Known Activations